AI news archive.
4,959 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsSciHorizon-eLab: An Agentic Protocol-to-Task Compiler for Scalable Benchmarking of Scientific Embodied Agents
arXiv:2609.30971v1 Announce Type: new Abstract: Embodied agents offer a promising route to automating scientific experimentation, yet their progress is constrained by the lack of reliable and systematic evaluation enviro…
- arXiv cs.AIagentsCheap, open agents make LLM pollution harder to mitigate
arXiv:2609.31054v2 Announce Type: replace Abstract: Large Language Model (LLM) pollution occurs when synthetic responses contaminate data intended to capture human behavior. High deployment costs have so far limited the…
- arXiv cs.AIagentsUp and Down the Abstraction Ladder: Code-Based Skills for Language Agents
arXiv:2609.31076v1 Announce Type: new Abstract: Language agents struggle to act and learn in environments that require long sequences of low-level actions. Code-based abstractions can make these agents more productive by…
- arXiv cs.AIagentsOmouAI: Argumentative Human-AI Policy Deliberation with Simulated Personas
arXiv:2609.31078v1 Announce Type: new Abstract: Debates amongst agents driven by large language models (LLMs) have demonstrated vast potential in various applications, but when these interactions include humans and take…
- arXiv cs.AIagentsToward AI-Augmented Cooperative Engineering Workflows: Requirements and Architecture the European Rover Challenge
arXiv:2609.31136v1 Announce Type: new Abstract: The growing availability of Artificial Intelligence (AI) tools creates new opportunities to support engineering design processes, yet their current use often remains limite…
- arXiv cs.AIagentsMomentum-Guided Federated Split Distillation for Personalized Temporal Edge Intelligence
arXiv:2609.31159v1 Announce Type: new Abstract: We propose a momentum-guided federated split distillation framework for personalized, efficient, and autonomous temporal edge intelligence. We introduce TeRR-SAtt, our nove…
- arXiv cs.AIagentsSemantic Navigation for Issue Localization in Code Repository
arXiv:2609.31176v1 Announce Type: new Abstract: Repository-level issue localization aims to identify and rank the files and functions relevant to resolving a reported issue. LLM agents approach this task iteratively: the…
- arXiv cs.AIagentsEvolutionary Safety of Recursive Self-Improving AI: Taxonomy, Risk Discovery, and Evaluation
arXiv:2609.31186v2 Announce Type: replace Abstract: Rapid advances in AI are bringing recursive self-improvement (RSI) closer to practice, with growing progress in model self-training, self-evolving agents, and automated…
- arXiv cs.AIagentsMA-WAM: Multi-Agent World-Action Model for Test-Time Planning
arXiv:2609.31281v1 Announce Type: new Abstract: Multi-agent cooperative tasks require different agents to execute a joint action simultaneously, and each agent's action affects both the observations and responses of the…
- arXiv cs.AIagentsG2MAF: Test-Time Gradient Guidance for Multi-Agent Flow Policies
arXiv:2609.31286v1 Announce Type: new Abstract: Offline multi-agent reinforcement learning (MARL) learns cooperative policies from fixed datasets without further environment interaction and a learned policy is frozen at…
- arXiv cs.AIagentsEvaluating Budgeted Context Projection with Unexecuted Companion Runs
arXiv:2609.31381v2 Announce Type: replace Abstract: Context projection can shorten individual requests while changing whether an agent finishes within its budget. We examine how sequential evaluation obscures this trade-…
- arXiv cs.AIagentsCompress What You See, Not What You Say: Anchored Context Distillation for Latent-Observation Software Engineering Agents
arXiv:2609.31430v1 Announce Type: new Abstract: Tool observations dominate the context of software-engineering agents, making long interaction histories costly to maintain. Existing context compression methods can discar…
- arXiv cs.AIagentsSegment-Level Agentic Topic Modeling for Improved Data Exploration and Resource Efficiency
arXiv:2609.31460v1 Announce Type: new Abstract: Topic modeling is an effective technique for discovering hidden themes within documents and is widely used in text mining and data analysis across a variety of industry sec…
- arXiv cs.AIagentsMulti-agent Scaling Across Disjunctive and Compensatory Tasks
arXiv:2609.31563v1 Announce Type: new Abstract: Multi-agent LLM systems are often expected to improve as team size increases, yet the scaling behavior may depend on task structure. Our central contribution is to introduc…
- arXiv cs.AIagentsDeepEdu-v1: Efficient and Scalable Agentic LLMs for Vietnamese Education
arXiv:2609.31568v1 Announce Type: new Abstract: AI tutoring could markedly improve learning outcomes for students in developing regions such as Vietnam, yet the two obvious paths both fall short. Cloud assistants such as…
- arXiv cs.AIagentsCartograph: Federated Tool Discovery with Operator-Attested Retrieval for AI Agents
arXiv:2609.30293v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) enables AI agents to discover and call tools, but loading every definition becomes expensive as connected catalogs grow. We present Carto…
- arXiv cs.AIagentsBootstrapping Conversational Recommendation Agents At Spotify: Synthetic Data Generation and Self-Improvement Loops
arXiv:2609.30297v1 Announce Type: cross Abstract: Conversational recommendation agents are a new paradigm for content discovery, enabling users to express complex intents through natural language (e.g., "recommend Italia…
- arXiv cs.AIagentsWhat Will Remain Human in Software Architecture? A Focus Group Report
arXiv:2609.30334v1 Announce Type: cross Abstract: AI development agents are increasingly used to support and partially automate software architecture tasks. To explore how practitioners perceive this shift, specifically…
- arXiv cs.AIagentsCoding Agents Aren't Enough! Evaluating an Enterprise Security Brain for Agentic Cloud Investigations
arXiv:2609.30345v2 Announce Type: replace-cross Abstract: Cloud-security investigation is dominated by population tasks: which identities can read a data store, how many resources fail a control, what is reachable from a…
- arXiv cs.AIagentsCARGO: Context-Aware Retrieval-Gated Evaluation of Agentic AI in Production
arXiv:2609.30471v1 Announce Type: cross Abstract: Reference-based LLM-as-a-judge evaluation assumes the reference answer is the target. In deployed agentic systems that operate over dynamic entities (support cases, asset…
- arXiv cs.AIagentsInquesto Score: A reliability Protocol For Voice Agents
arXiv:2609.30514v1 Announce Type: cross Abstract: Voice agents are increasingly deployed in workflows where failed interactions can affect transactions, access, and other consequential outcomes, creating a need for repro…
- arXiv cs.AIagentsAuditing Latent-Space Monitors for Autonomous Driving
arXiv:2609.30557v1 Announce Type: cross Abstract: Runtime failure monitors can use a model's internal representations to anticipate failures. We audit this monitoring strategy across two autonomous-driving tasks: online…
- arXiv cs.AIagentsProbing Stability-Plasticity Tradeoffs in Agent Memory through Cognitive Experimental Paradigms
arXiv:2609.30558v1 Announce Type: cross Abstract: Agent memory systems are increasingly used to maintain long-term user preferences, task states and evolving facts, but current evaluations often collapse memory behavior…
- arXiv cs.AIagentsThe Hard Part Comes After Search: Benchmarking Web Agents on Synthesizing, Organizing, and Displaying Knowledge
arXiv:2609.30604v1 Announce Type: cross Abstract: Existing computer-use agent benchmarks do not fully evaluate agents acting as assistants. A useful assistant retrieves information across complex, multi-step workflows, s…
- arXiv cs.AIagentsSubjects, Not Authors: The Authorship Hazard in Agentic Dataspaces
arXiv:2609.30614v2 Announce Type: replace-cross Abstract: Dataspace connectors decide whether a transfer may occur, not what the transferred value contains, tolerable for contracted applications, not for LLM agents that…
- arXiv cs.AIagentsA Framework for Identifying, Categorizing, and Explaining Bias in AI-Generated Code
arXiv:2609.30642v1 Announce Type: cross Abstract: As Large Language Models (LLMs) become integrated into software development workflows, concerns regarding unintentional biases in AI-generated code. Although evidence sug…
- arXiv cs.AIagentsCausal Retention in Interactive Agents: Interface Factorization and Selective Adaptation
arXiv:2609.30650v1 Announce Type: cross Abstract: Task performance need not determine which intervention mechanism an agent retains. We study causal retention: whether a frozen learned state answers a mechanism-probe map…
- arXiv cs.AIagentsThreat-Aware Energy-Efficient Deployment for Dynamic UAV Networks: A Multi-Agent RL Approach
arXiv:2609.30690v1 Announce Type: cross Abstract: Ensuring operational safety in threat-prone environments remains a critical challenge for multi-UAV networks serving as aerial base stations. This paper proposes an effic…
- arXiv cs.AIagentsSkip the Talk, Re-Focus on Vision: Latent Reasoning for Reasoning Segmentation in Multimodal Large Language Models
arXiv:2609.30783v1 Announce Type: cross Abstract: Reasoning segmentation aims to interpret implicit textual queries and enable fine-grained visual perception, which is critical for applications such as human-computer int…
- arXiv cs.AIagentsEvaluation Is All You Need for Multi-Modal Autonomous Driving
arXiv:2609.30818v1 Announce Type: cross Abstract: Multi-modal planning is promising for autonomous driving by representing multiple plausible behaviors in ambiguous and long-tail scenarios. Existing methods mainly focus…
- arXiv cs.AIagentsDeveloping a Roadmap to an AI-first Organization: A Case Study in Embedded Software Development
arXiv:2609.30863v1 Announce Type: cross Abstract: The emergence of AI agents is expected to reshape software engineering by moving beyond AI as assistants towards systems capable of planning, executing, and evaluating de…
- arXiv cs.AIagentsWarned alike, AI agents avoid the less-crowded road while people take it
arXiv:2609.30883v1 Announce Type: cross Abstract: AI agents built on a few shared models increasingly act for many people. A shared forecast about others can align their choices and change how scarce capacity is allocate…
- arXiv cs.AIagentsDynBranch: Speculative Subgraph Reuse for Dynamic Agentic LLM Serving
arXiv:2609.31047v1 Announce Type: cross Abstract: Agentic LLM workflows decide their execution paths at runtime. Downstream computation may be predictable, or may have run before, yet it cannot begin until the model or t…
- arXiv cs.AIagentsAgentRecommender: LLM Agents Enable Customizable Recommender Systems on the User Side
arXiv:2609.31166v1 Announce Type: cross Abstract: Recommender systems have traditionally been developed for platforms. However, this has given rise to many phenomena that may be advantageous for platform lock-in but are…
- arXiv cs.AIagentsAgentic Limit Order Books: Phase Transitions and Market Impact
arXiv:2609.31260v1 Announce Type: cross Abstract: We investigate the systemic macroscopic dynamics emerging from Limit Order Books (LOBs) populated exclusively by autonomous reinforcement-learning agentic traders. By for…
- arXiv cs.AIagentsCognitive Skills in the Age of AI: Computing Students and Experts Perceptions
arXiv:2609.31272v2 Announce Type: replace-cross Abstract: AI is becoming increasingly integrated into daily workflows, especially in computing. We are gradually shifting towards an AI-rich future, an impending yet unknow…
- arXiv cs.AIagentsResource-Optimized and Energy-Aware Agentic AI Framework Anchored on Blockchain for Secure Software Supply Chains
arXiv:2609.31282v1 Announce Type: cross Abstract: This paper proposes a blockchain-backed agentic security framework designed to safeguard the complete software development lifecycle (SDLC) while also securing the agenti…
- arXiv cs.AIagentsBeyond Approved Actions: Runtime Validation of Persistent Outcomes in Agent Workflows
arXiv:2609.31301v1 Announce Type: cross Abstract: Large language model agents increasingly act on software systems, no longer merely generating text but also changing databases and online services. However, an approved d…
- arXiv cs.AIagentsAgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI Agents
arXiv:2609.31318v1 Announce Type: cross Abstract: AI agents combine language models with external data and tools that can modify files, call APIs, or execute code. Security failures can arise when adversarial content cha…
- arXiv cs.AIagentsCG-HAF: An Interpretable Global-Local Lesion-Burden Fusion Framework for Ordinal Acne Severity Grading in Agentic Skincare Support
arXiv:2609.31326v1 Announce Type: cross Abstract: Ordinal acne severity grading requires distinguishing visually similar neighboring grades while jointly weighing holistic facial appearance and localized lesion burden -…
- arXiv cs.AIagentsA Safety-Bounded SDC-to-MCP Gateway for Medical AI Agents
arXiv:2609.31358v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) provides a common interface through which AI applications discover and use external resources and tools. It allows language-model agents…
- arXiv cs.AIagentsActKV: Efficient LLM Agents through Action-Guided KV Cache Management
arXiv:2609.31395v1 Announce Type: cross Abstract: Agentic LLM inference accumulates long KV caches across iterative observation-reasoning-action loops, imposing substantial memory overhead and limiting serving throughput…
- arXiv cs.AIagentsTowards Mitigating Fabricated Consensus: The Active Provenance Gate for Multi-Agent Debate Synthesis
arXiv:2609.31422v1 Announce Type: cross Abstract: Large language model-based multi-agent debate (MAD) systems are being increasingly used as complex decision pipelines in distributed processes. However, their final synth…
- arXiv cs.AIagentsPriceBench: A Diagnostic Benchmark for Price, Quality, and Brand Preferences in LLM Booking Agents
arXiv:2609.31468v1 Announce Type: cross Abstract: LLMs increasingly act as purchasing agents, which makes the LLM, not the user, the one choosing among the options that satisfy a request; its preferences quietly fix what…
- arXiv cs.AIagentsCompact Documentation for Coding Agents: A Benchmark, an Optimizer, and Why It Does Not Transfer
arXiv:2609.31587v1 Announce Type: cross Abstract: We investigate whether natural-language documentation helps coding agents resolve software issues, and we build the tools to construct and evaluate it. We introduce a rou…
- arXiv cs.AIagentsPreference-based opponent shaping in differentiable games
arXiv:2412.03072v2 Announce Type: replace Abstract: Strategy learning in game environments with multi-agent is a challenging problem. Since each agent's reward is determined by the joint strategy, a greedy learning strat…
- arXiv cs.AIagentsSkillFlow: Scalable and Efficient Agent Skill Retrieval System
arXiv:2504.06188v3 Announce Type: replace Abstract: AI agents can extend their capabilities at inference time by loading reusable skills into context, yet equipping an agent with too many skills, particularly irrelevant…
- arXiv cs.AIagentsThe Plot Twist: Jailbreaking Unified Multimodal Models with a Three-Act NarrativeAttack
arXiv:2509.26473v2 Announce Type: replace Abstract: Unified Multimodal Understanding and Generation Models (UMMs) increasingly combine visual understanding and image generation within a single interactive workflow, makin…
- arXiv cs.AIagentsFlyAOC: Evaluating Agentic Ontology Curation of Drosophila Scientific Knowledge Bases
arXiv:2602.09163v2 Announce Type: replace Abstract: Scientific knowledge bases accelerate discovery by curating findings from primary literature into structured, queryable formats for both human researchers and emerging…
- arXiv cs.AIagentsGT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory
arXiv:2602.12316v3 Announce Type: replace Abstract: Frontier AI systems are increasingly capable and deployed in high-stakes multi-agent environments. However, existing AI safety benchmarks largely evaluate single agents…